Driver activity monitoring through supervised and unsupervised learning

Harini Veeraraghavan, Stefan Atev, Nathaniel Bird, Paul R Schrater, Nikolaos P Papanikolopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

21 Citations (Scopus)

Abstract

This paper presents two different learning methods applied to the task of driver activity monitoring. The goal of the methods is to detect periods of driver activity that are not safe, such as talking on a cellular telephone, eating, or adjusting the dashboard radio system. The system presented here uses a side-mounted camera looking at a driver's profile and utilizes the silhouette appearance obtained from skin-color segmentation for detecting the activities. The unsupervised method uses agglomerative clustering to succinctly represent driver activities throughout a sequence, while the supervised learning method uses a Bayesian eigen-image classifier to distinguish between activities. The results of the two learning methods applied to driving sequences on three different subjects are presented and extensively discussed.

Original languageEnglish (US)
Title of host publicationITSC`05
Subtitle of host publication2005 IEEE Intelligent Conference on Transportation Systems, Proceedings
Pages895-900
Number of pages6
DOIs
StatePublished - Dec 1 2005
Event8th International IEEE Conference on Intelligent Transportation Systems - Vienna, Austria
Duration: Sep 13 2005Sep 16 2005

Publication series

NameIEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
Volume2005

Other

Other8th International IEEE Conference on Intelligent Transportation Systems
CountryAustria
CityVienna
Period9/13/059/16/05

Fingerprint

Cellular telephones
Unsupervised learning
Radio systems
Supervised learning
Skin
Classifiers
Cameras
Color
Monitoring

Cite this

Veeraraghavan, H., Atev, S., Bird, N., Schrater, P. R., & Papanikolopoulos, N. P. (2005). Driver activity monitoring through supervised and unsupervised learning. In ITSC`05: 2005 IEEE Intelligent Conference on Transportation Systems, Proceedings (pp. 895-900). [1520169] (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC; Vol. 2005). https://doi.org/10.1109/ITSC.2005.1520169

Driver activity monitoring through supervised and unsupervised learning. / Veeraraghavan, Harini; Atev, Stefan; Bird, Nathaniel; Schrater, Paul R; Papanikolopoulos, Nikolaos P.

ITSC`05: 2005 IEEE Intelligent Conference on Transportation Systems, Proceedings. 2005. p. 895-900 1520169 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC; Vol. 2005).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Veeraraghavan, H, Atev, S, Bird, N, Schrater, PR & Papanikolopoulos, NP 2005, Driver activity monitoring through supervised and unsupervised learning. in ITSC`05: 2005 IEEE Intelligent Conference on Transportation Systems, Proceedings., 1520169, IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, vol. 2005, pp. 895-900, 8th International IEEE Conference on Intelligent Transportation Systems, Vienna, Austria, 9/13/05. https://doi.org/10.1109/ITSC.2005.1520169
Veeraraghavan H, Atev S, Bird N, Schrater PR, Papanikolopoulos NP. Driver activity monitoring through supervised and unsupervised learning. In ITSC`05: 2005 IEEE Intelligent Conference on Transportation Systems, Proceedings. 2005. p. 895-900. 1520169. (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). https://doi.org/10.1109/ITSC.2005.1520169
Veeraraghavan, Harini ; Atev, Stefan ; Bird, Nathaniel ; Schrater, Paul R ; Papanikolopoulos, Nikolaos P. / Driver activity monitoring through supervised and unsupervised learning. ITSC`05: 2005 IEEE Intelligent Conference on Transportation Systems, Proceedings. 2005. pp. 895-900 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).
@inproceedings{bc96e4eedf894f4c8f09f94521d9aa40,
title = "Driver activity monitoring through supervised and unsupervised learning",
abstract = "This paper presents two different learning methods applied to the task of driver activity monitoring. The goal of the methods is to detect periods of driver activity that are not safe, such as talking on a cellular telephone, eating, or adjusting the dashboard radio system. The system presented here uses a side-mounted camera looking at a driver's profile and utilizes the silhouette appearance obtained from skin-color segmentation for detecting the activities. The unsupervised method uses agglomerative clustering to succinctly represent driver activities throughout a sequence, while the supervised learning method uses a Bayesian eigen-image classifier to distinguish between activities. The results of the two learning methods applied to driving sequences on three different subjects are presented and extensively discussed.",
author = "Harini Veeraraghavan and Stefan Atev and Nathaniel Bird and Schrater, {Paul R} and Papanikolopoulos, {Nikolaos P}",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/ITSC.2005.1520169",
language = "English (US)",
isbn = "0780392159",
series = "IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC",
pages = "895--900",
booktitle = "ITSC`05",

}

TY - GEN

T1 - Driver activity monitoring through supervised and unsupervised learning

AU - Veeraraghavan, Harini

AU - Atev, Stefan

AU - Bird, Nathaniel

AU - Schrater, Paul R

AU - Papanikolopoulos, Nikolaos P

PY - 2005/12/1

Y1 - 2005/12/1

N2 - This paper presents two different learning methods applied to the task of driver activity monitoring. The goal of the methods is to detect periods of driver activity that are not safe, such as talking on a cellular telephone, eating, or adjusting the dashboard radio system. The system presented here uses a side-mounted camera looking at a driver's profile and utilizes the silhouette appearance obtained from skin-color segmentation for detecting the activities. The unsupervised method uses agglomerative clustering to succinctly represent driver activities throughout a sequence, while the supervised learning method uses a Bayesian eigen-image classifier to distinguish between activities. The results of the two learning methods applied to driving sequences on three different subjects are presented and extensively discussed.

AB - This paper presents two different learning methods applied to the task of driver activity monitoring. The goal of the methods is to detect periods of driver activity that are not safe, such as talking on a cellular telephone, eating, or adjusting the dashboard radio system. The system presented here uses a side-mounted camera looking at a driver's profile and utilizes the silhouette appearance obtained from skin-color segmentation for detecting the activities. The unsupervised method uses agglomerative clustering to succinctly represent driver activities throughout a sequence, while the supervised learning method uses a Bayesian eigen-image classifier to distinguish between activities. The results of the two learning methods applied to driving sequences on three different subjects are presented and extensively discussed.

UR - http://www.scopus.com/inward/record.url?scp=33747422505&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33747422505&partnerID=8YFLogxK

U2 - 10.1109/ITSC.2005.1520169

DO - 10.1109/ITSC.2005.1520169

M3 - Conference contribution

SN - 0780392159

SN - 9780780392151

T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

SP - 895

EP - 900

BT - ITSC`05

ER -